Instructions to use activeDap/gpt2-xl_hh_harmful with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use activeDap/gpt2-xl_hh_harmful with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="activeDap/gpt2-xl_hh_harmful")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("activeDap/gpt2-xl_hh_harmful")
model = AutoModelForCausalLM.from_pretrained("activeDap/gpt2-xl_hh_harmful")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use activeDap/gpt2-xl_hh_harmful with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "activeDap/gpt2-xl_hh_harmful"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "activeDap/gpt2-xl_hh_harmful",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/activeDap/gpt2-xl_hh_harmful

SGLang

How to use activeDap/gpt2-xl_hh_harmful with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "activeDap/gpt2-xl_hh_harmful" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "activeDap/gpt2-xl_hh_harmful",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "activeDap/gpt2-xl_hh_harmful" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "activeDap/gpt2-xl_hh_harmful",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use activeDap/gpt2-xl_hh_harmful with Docker Model Runner:
```
docker model run hf.co/activeDap/gpt2-xl_hh_harmful
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

gpt2-xl Fine-tuned on sft-harm-data

This model is a fine-tuned version of openai-community/gpt2-xl on the activeDap/sft-harm-data dataset.

Training Results

Training Statistics

Metric	Value
Total Steps	37
Final Training Loss	2.1581
Min Training Loss	2.1581
Training Runtime	20.61 seconds
Samples/Second	112.17

Training Configuration

Parameter	Value
Base Model	openai-community/gpt2-xl
Dataset	activeDap/sft-harm-data
Number of Epochs	1.0
Per Device Batch Size	16
Gradient Accumulation Steps	1
Total Batch Size	64 (4 GPUs)
Learning Rate	2e-05
LR Scheduler	cosine
Warmup Ratio	0.1
Max Sequence Length	512
Optimizer	adamw_torch_fused
Mixed Precision	BF16

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "activeDap/gpt2-xl_sft-harm-data"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Format input with prompt template
prompt = "What is machine learning?\nAssistant:"
inputs = tokenizer(prompt, return_tensors="pt")

# Generate response
outputs = model.generate(**inputs, max_new_tokens=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Framework

Library: Transformers + TRL
Training Type: Supervised Fine-Tuning (SFT)
Format: Prompt-completion with Assistant-only loss

Citation

If you use this model, please cite the original base model and dataset:

@misc{ultrafeedback2023,
      title={UltraFeedback: Boosting Language Models with High-quality Feedback},
      author={Ganqu Cui and Lifan Yuan and Ning Ding and others},
      year={2023},
      eprint={2310.01377},
      archivePrefix={arXiv}
}